Search

In this chapter, a dexterous robot hand is proposed based on the design concepts of light weight, compact size, similar to human's hand gripping motions, gripping force restriction, and low cost. The robot hand prototype is produced in this study. Especially, complicated kinematics models and position control of joint angles are not constructed due to unpredictable object orientations and positions in this study. Instead, the gripping motion behavior models for different gripping motions cooperating with maximum allowable tactile forces and joint angles are constructed to simplify the control architecture as well as to improve the practical gripping compatibility. This chapter just represent a pilot study of a low cost dexterous robot hand; however, most of design and control parameters are not well justified to perform perfect performance. On the other hand, the selection of tendon wire as well as the mechanical properties and dynamics of the tendon wire are still the major interests of the future works.

This chapter presents the navigation technologies of mobility assistive robots for disabled patients. The autonomous navigations of conventional robotic wheelchairs are not easy to be implemented because the inconvenience of setting target positions for each segmental path, and unavailable global localization and map of environment. Therefore, a feasible robotic wheelchair is achieved by controlling the wheelchair using the joystick, and the hybrid function converts joystick command as the virtual target for the fuzzy based navigation functions. In this manner, the proposed navigation functions become important assistive function to justify user's command and to perform more safe and comfortable wheelchair driving mechanism. On the other hand, a PSoC based distributed computing architecture is implemented to control the robotic wheelchairs. The proposed architecture is proposed to reduce the costs, size, and power consumptions and to increase the reliability of the popular PC based navigation system. Experiment results validated the PSoC based navigation functions. Based on practical experiments, the computational error is within 8 % and the time elapsed for computation and communication traffic is within 0.14 second. More specially, the proposed architecture is more feasible than the PC based navigation system. In the future, the navigation algorithm will be optimized to increase the computational efficiency and accuracy as well. At the same, in-hospital test will be planned to verify the clinical effectiveness.

Accurate segmentation of drivable areas and road obstacles is critical for autonomous mobile robots to navigate safely in indoor and outdoor environments. With the fast advancement of deep learning, mobile robots may now perform autonomous navigation based on what they learned in the learning phase. On the other hand, existing techniques often have low performance when confronted with complex situations since unfamiliar objects are not included in the training dataset. Additionally, the use of a large amount of labeled data is generally essential for training deep neural networks to achieve good performance, which is time-consuming and labor-intensive. Thus, this paper presents a solution to these issues by proposing a self-supervised learning method for the drivable areas and road anomaly segmentation. First, we propose the Automatic Generating Segmentation Label (AGSL) framework, which is an efficient system automatically generating segmentation labels for drivable areas and road anomalies by finding dissimilarities between the input and resynthesized image and localizing obstacles in the disparity map. Then, we train RGB-D datasets with a semantic segmentation network using self-generated ground truth labels derived from our method (AGSL labels) to get the pre-trained model. The results showed that our AGSL achieved high performance in labeling evaluation, and the pre-trained model also obtains certain confidence in real-time segmentation application on mobile robots.

This paper presents a mechatronic P300-based brain computer interface (BCI) for wheelchair control applications. A translucent visual stimulus panel (TVSP) is set up in front of the wheelchair to provide an intuitive P300 visual stimulus operation as well as to realize the see-through scene during operating wheelchairs. In this research, a micro projector is utilized to produce flickering visual stimuli on the display board which is 35cm away from the user. To improve the information transfer rate (ITR), a spatial filter based on Canonical Correlation Analysis (CCA) and Support Vector Machine (SVM) were also applied to this work to improve the performance of BCI classification. The result of experiments showed that the proposed BCI is with 88.2% in accuracy and 22.97 bits/min information transfer rate in average received from ten subjects. In ground truth experiments of practical trajectory tracking, the root mean squared error (RMSE) of P300 BCI are 12.11cm in “U” trajectory test.

The government of Taiwan is pursuing a national strategy focused on the Fourth Industrial Revolution and the associated developments in advanced manufacturing. As part of this strategy, the government is working with the secondary schools and with colleges to improve STEM education experiences and develop the country’s talent pipeline. This case shares the experience of FIRST Robotics Team 6191 TFG from Taipei First Girls High School, highlighting the educational approach, rich outside-school collaborations, and the manner in which the national government has engaged the teachers and students as leaders for the national effort. The case also shares the experience of National Taiwan University of Science and Technology (NTUST), also known as Taiwan Tech, and how NTUST is using a hands-on STEM tools to teach college students to learn knowledge and skills needed to design and manage production processes. A Taiwan-specific model of the STEM Technopolis virtuous cycle is shared.

BACKGROUND Local hospitals must deal with large numbers of patients during mass casualty incidents, and the wireless sensor networks (WSNs) can help in these situations by monitoring vital signs. Conventional ZigBee nodes can obtain the ID of a device by assigning a unique 16-bit short address or by burning firmware into an IC. These methods tend to complicate node management and lack portability. OBJECTIVE The study developed a node management mechanism to deal with a large number of patients in real-time, through the wireless monitoring of physiological signals. The mechanism proposed for the ZigBee WSN is based on a three-layer (Coordinator, Control Router, and End Device) tree topology. METHODS The proposed system includes a node deployment process to formulate a ZigBee WSN as a tree topology, an algorithm to automatically number ZigBee nodes for monitoring and control system (MCS), and an algorithm to automatically obtain the short addresses of nodes for data collection. Specifically, an algorithm automatically collects data from ZigBee nodes for display on a computer graphical user interface (GUI). We also developed a reliable data transmission method capable of resolving the problem of packet loss. RESULTS The proposed method has been applied in a local hospital. Our research findings provide a valuable reference for the development of ZigBee-based MCS. CONCLUSIONS The proposed node management mechanism is faster, more reliable, and more intuitive to use, than traditional methods.

This paper presents the implementation of an autonomous electric vehicle (EV) project in the National Taiwan University of Science and Technology (NTUST) campus in Taiwan. The aim of this work was to integrate two important practices of realizing an autonomous vehicle in a campus environment, including vehicle positioning and path tracking. Such a project is helpful to the students to learn and practice key technologies of autonomous vehicles conveniently. Therefore, a laboratory-made EV was equipped with real-time kinematic GPS (RTK-GPS) to provide centimeter position accuracy. Furthermore, the model predictive control (MPC) was proposed to perform the path tracking capability. Nevertheless, the RTK-GPS exhibited some robust positioning concerns in practical application, such as a low update rate, signal obstruction, signal drift, and network instability. To solve this problem, a multisensory fusion approach using an unscented Kalman filter (UKF) was utilized to improve the vehicle positioning performance by further considering an inertial measurement unit (IMU) and wheel odometry. On the other hand, the model predictive control (MPC) is usually used to control autonomous EVs. However, the determination of MPC parameters is a challenging task. Hence, reinforcement learning (RL) was utilized to generalize the pre-trained datum value for the determination of MPC parameters in practice. To evaluate the performance of the RL-based MPC, software simulations using MATLAB and a laboratory-made, full-scale electric vehicle were arranged for experiments and validation. In a 199.27 m campus loop path, the estimated travel distance error was 0.82% in terms of UKF. The MPC parameters generated by RL also achieved a better tracking performance with 0.227 m RMSE in path tracking experiments, and they also achieved a better tracking performance when compared to that of human-tuned MPC parameters.

In the industrial environment, Autonomous Guided Vehicles (AGVs) generally run on a planned route. Among trajectory-tracking algorithms for unmanned vehicles, the Pure Pursuit (PP) algorithm is prevalent in many real-world applications because of its simple and easy implementation. However, it is challenging to decelerate the AGV’s moving speed when turning on a large curve path. Moreover, this paper addresses the kidnapped-robot problem occurring in spare LiDAR environments. This paper proposes an improved Pure Pursuit algorithm so that the AGV can predict the trajectory and decelerate for turning, thus increasing the accuracy of the path tracking. To solve the kidnapped-robot problem, we use a learning-based classifier to detect the repetitive pattern scenario (e.g., long corridor) regarding 2D LiDAR features for switching the localization system between Simultaneous Localization And Mapping (SLAM) method and Odometer method. As experimental results in practice, the improved Pure Pursuit algorithm can reduce the tracking error while performing more efficiently. Moreover, the learning-based localization selection strategy helps the robot navigation task achieve stable performance, with 36.25% in completion rate more than only using SLAM. The results demonstrate that the proposed method is feasible and reliable in actual conditions.

P300 is a brain–computer interface (BCI) modality which reflects brains’ processes in stimulus events. Visual stimuli are usually used to elicit event-related P300 components. However, depending on different subjects’ conditions and their current cerebral loads, P300 components occur at posterior to stimuli from 250 to 600 ms roughly. These subjects’ dependent variations affect the performance of BCI. Thus, an estimation model that estimated an appropriate interval for P300 feature extraction is discussed in this paper. An interval type-2 fuzzy logic system trained by artificial bee-colony algorithm was used to find the latency of elicited P300 with a certain range by means of steady-state visually evoked potential. A support vector machine classifier was adopted to classify extracted epochs into target and non-target stimuli. Seven subjects were involved in experiments. Results showed that the performance of information transfer rate was improved by 1.28 % on average if the proposed latency-estimation approach was introduced.

This paper addresses the end-effector position and orientation tracking problem of a 6-degrees of freedom (DOF) rigid link electrically driven (RLED) revolute joint serial robot manipulator with uncertain parameters and external disturbances. System uncertainties and external disturbances are bounded but their upper limits are unknown. The input matrix, which is always invertible and not necessarily a diagonal matrix, is also assumed to be uncertain with a certain bound. An adaptive sliding mode control (ASMC) is designed to solve the tracking problem given these uncertainties. Note that the designed control method can be applied to any RLED serial robot manipulator. No regression matrices are required and the uncertainty upper limits are not necessarily known. Furthermore, the controller computation time can be reduced by considering some parts of the system dynamics and the nth time-derivative reference signals of nth order system, in this case desired joint jerk signals, as unknown bounded uncertainties. The desired trajectory is defined in operational space while the designed ASMC works in joint space. The methods to convert the end-effector pose, velocity, acceleration, and jerk from operational space to joint space are also explained. The Lyapunov stability criterion is applied to prove the convergence of the adaptive gain of ASMC, the sliding surface, and system stability. Finally, simulation results verified ASMC performance.

Improving the independent living ability of people who have suffered spinal cord injuries (SCIs) is essential for their quality of life. Brain-computer interfaces (BCIs) provide promising solutions for people with high-level SCIs. This paper proposes a novel and practical P300-based hybrid stimulus-on-device (SoD) BCI architecture for wireless networking applications. Instead of a stimulus-on-panel architecture (SoP), the proposed SoD architecture provides an intuitive control scheme. However, because P300 recognitions rely on the synchronization between stimuli and response potentials, the variation of latency between target stimuli and elicited P300 is a concern when applying a P300-based BCI to wireless applications. In addition, the subject-dependent variation of elicited P300 affects the performance of the BCI. Thus, an adaptive model that determines an appropriate interval for P300 feature extraction was proposed in this paper. Hence, this paper employed the artificial bee colony- (ABC-) based interval type-2 fuzzy logic system (IT2FLS) to deal with the variation of latency between target stimuli and elicited P300 so that the proposed P300-based SoD approach would be feasible. Furthermore, the target and nontarget stimuli were identified in terms of a support vector machine (SVM) classifier. Experimental results showed that, from five subjects, the performance of classification and information transfer rate were improved after calibrations (86.00% and 24.2 bits/ min before calibrations; 90.25% and 27.9 bits/ min after calibrations).

This chapter introduces Petri-net-based wireless sensor-node architecture (PN-WSNA) to model the execution behaviors of a sensor node according to the tasks it needs to accomplish. It illustrates the modeling of PN-WSNA and theoretical equivalencies. The chapter demonstrates some PN-WSNA examples and describes the user interface of the PN-WSNA integrated development environment. It explains the fundamental PN-WSNA models of sensor places, high/low-enable transitions, transmitter and receiver places, actuation places, and timed transitions are presented. The chapter presents a simple 2-to-4 multiplexer PN-WSNA logic model is proposed for evaluating a combinational reasoning system. With the PN-WSNA–based WSN system implementation approaches, the WSN engineers can focus on the execution scenario models instead of programming complicated platform-specific applications. With the benefits of virtual machine and model-based implementation approaches, the reconfiguration of existing sensor nodes is accomplished by reloading the PN-WSNA models, and no physical sensor-node visits are needed.

This paper presents an oscillometric blood pressure (BP) measurement approach based on the active control schemes of cuff pressure. Compared with conventional electronic BP instruments, the novelty of the proposed BP measurement approach is to utilize a variable volume chamber which actively and stably alters the cuff pressure during inflating or deflating cycles. The variable volume chamber is operated with a closed-loop pressure control scheme, and it is activated by controlling the piston position of a single-acting cylinder driven by a screw motor. Therefore, the variable volume chamber could significantly eliminate the air turbulence disturbance during the air injection stage when compared to an air pump mechanism. Furthermore, the proposed active BP measurement approach is capable of measuring BP characteristics, including systolic blood pressure (SBP) and diastolic blood pressure (DBP), during the inflating cycle. Two modes of air injection measurement (AIM) and accurate dual-way measurement (ADM) were proposed. According to the healthy subject experiment results, AIM reduced 34.21% and ADM reduced 15.78% of the measurement time when compared to a commercial BP monitor. Furthermore, the ADM performed much consistently (i.e., less standard deviation) in the measurements when compared to a commercial BP monitor.

A high efficient time-shift correlation algorithm was proposed to deal with the peak time uncertainty of P300 evoked potential for a P300-based brain-computer interface (BCI). The time-shift correlation series data were collected as the input nodes of an artificial neural network (ANN), and the classification of four LED visual stimuli was selected as the output node. Two operating modes, including fast-recognition mode (FM) and accuracy-recognition mode (AM), were realized. The proposed BCI system was implemented on an embedded system for commanding an adult-size humanoid robot to evaluate the performance from investigating the ground truth trajectories of the humanoid robot. When the humanoid robot walked in a spacious area, the FM was used to control the robot with a higher information transfer rate (ITR). When the robot walked in a crowded area, the AM was used for high accuracy of recognition to reduce the risk of collision. The experimental results showed that, in 100 trials, the accuracy rate of FM was 87.8% and the average ITR was 52.73 bits/min. In addition, the accuracy rate was improved to 92% for the AM, and the average ITR decreased to 31.27 bits/min. due to strict recognition constraints.

In this paper, the Petri net-based wireless sensor node architecture (PN-WSNA) is used to control a humanoid robot to play weightlifting and sprint games in the FIRA HuroCup league. With the PN-WSNA approach, the control scenario and decision-making for playing weightlifting and sprint games can be modeled as a PN-WSNA model. The PN-WSNA inference engine is further used to interpret and execute the PN-WSNA model according to the sensor information from visual perception. Therefore, the implementation of playing weightlifting and sprint games is achieved in terms of the PN-WSNA model instead of native code. To verify the PN-WSNA-based implementation approach, an autonomous humanoid robot equipped with a camera and a single-board computer is used for experiments, where the camera is responsible for grabbing image frames; the single-board computer is responsible for visual localization; and the PN-WSNA models the execution and locomotion command generation. Finally, several PN-WSNA models for playing weightlifting and sprint games are proposed and the experimental results are demonstrated and discussed to validate the feasibility of applying the proposed PN-WSNA-based implementation approach.

Objective: To examine postural alignment in children with bilateral spastic cerebral palsy while driving a powered wheelchair using both a unilateral joystick and an innovative bimanual interface. Design: Cross-sectional study. Subjects: A total of 20 children with bilateral spastic cerebral palsy (mean age 9.0 years (standard deviation 2.1); 11 with diplegia, 9 with quadriplegia) and 14 typically developing children (mean age 7.7 years (standard deviation 2.9)). Methods: All children drove the powered wheelchair in both the unilateral and bimanual conditions. The Seated Postural Control Measure quantified the postural alignment of subjects while driving the powered wheelchair. Statistical analysis was carried out using repeated measures analysis of variance and Spearman’s rank correlation coefficient. Results: As expected, typically developing children had better postural alignment in both driving conditions than children with cerebral palsy. Children with cerebral palsy demonstrated more symmetrical postural alignment while using the bimanual interface than when using the unilateral joystick. In addition, the severity of cerebral palsy correlated moderately with postural symmetry in both conditions. Conclusion: The results suggest that this innovative bimanual interface might be beneficial for promoting symmetrical postural alignment in some children with bilateral spastic cerebral palsy.

ZigBee wireless sensor devices possess characteristics of small size, light weight, low power consumption, having up to 65535 nodes in a sensor network, in theory. Therefore, the ZigBee wireless sensor network (WSN) is very suitable for use in developing monitoring and control (MC) applications, such as remote healthcare, industrial control, fire detection, environmental monitoring, and so on. This dissertation is directed towards the research on the issues of communication extension and backup, encountered in creating ZigBee-based MC systems for military storerooms, together with providing associated solutions. We design an embedded gateway that possesses wired network (Ethernet) and wireless communication (GSM) backup capability. The gateway can not only easily extend the monitoring distance of the ZigBee-based MCS, but can also solve the problem that some military zones do not have wire networks or possess communication blind spots. The results of this dissertation have been practically applied in constructing a paradigm monitoring system of a military storeroom. It is believed that the research results could be a useful reference for developing ZigBee-based MCSs in the future.

Biped humanoid robots present perception and locomotion capabilities similar to those of human beings. Eye-hand-leg coordination is a basic and required capability for a healthy person, and eye-hand-leg coordination performs various skill-oriented tasks. In this paper, the skill-oriented tasks for playing a basketball game were implemented for a child-size humanoid robot (HuroEvolution) through the use of eye-hand-leg coordination. The “eye” function is responsible for active perceptions in environments, the “hand” function is for gripping and manipulating objects to perform specific tasks, and the “leg” function is used to transport the biped robot to a desired location for the execution of tasks. Coordination among the eye, hand, and leg was achieved using predefined scenarios for various skill-oriented tasks. To utilize flexible and systematic skill-oriented task implementations, a Petri net-based wireless sensor node architecture (PN-WSNA) was employed in this project to define the task scenarios. The control scenario of eye-hand-leg coordination was realized by aggregating fundamental PN-WSNA scenario modules for fast realizations. The coordination model can be further evaluated theoretically to investigate its propensity for avoiding system deadlocks. Finally, the skill-oriented eye-hand-leg coordination tasks for realizing the Federation of International Robot-Soccer Association HuroCup League basketball games were successfully demonstrated to validate our approaches.

In this paper, we propose a wTouch interface for controlling a human-centered intelligent wheelchair. The wTouch interface is a touch panel which performs similar joystick manipulations while it provides convenient wheelchair control interface, as well as offers useful wheelchair status. In addition, reactive navigation techniques are also developed by combining with the obstacle information to perform collision free navigations. The obstacle detection sensor uses a laser range finder and the reactive navigation uses the artificial potential field approach. Finally, a wTouch wheelchair prototype is produced in our laboratory for evaluating the performance of reactive navigations.

Locomotion controller is an important and essential aspect for bipedal robots. Typically, a Linear Inverted Pendulum Model (LIPM) is a mathematical approach to generate the Center of Mass (CoM) trajectory of a bipedal robot. By combining the swing foot trajectory, the omni-directional walking command is capable of generating joint angle control commands in terms of Inverse Kinematics (IK). To improve bipedal locomotion stability on uneven terrain situations, an Inertia Measurement Unit (IMU) was desired to place on the robot's chest was used to measure the body's tilt posture on uneven terrains. The robot body's tilt posture provided an indication of locomotion stability. The body's tilt posture information was further evaluated with a Fuzzy Logic Controller (FLC) to generate appropriate offset angles to be applied on the corresponding joints so that the body's tilt posture can be adjusted accordingly to meet a stable situation. Finally, a kid-size bipedal robot, named Huro Evolution JR, was used as the experiment platform. The proposed FLC can be applicable to the terrain conditions of maximum 25° slope in Double Support Phased (DSP) stand cases. With the walking cases, the FLC is capable of walking on maximum 12° slope, 1 cm stair height and the combined terrain situation well. In the future, the Center of Pressure (CoP) information will be accompanied with the IMU information to further improved the locomotion stability in a high dynamic environment.

This study investigated microcirculatory-blood-flow responses in nude mice following the injection of CT26 tumor cells by analyzing the frequency content of skin blood-flow signals recorded on the skin surface. CT26 cells were injected subcutaneously (10^4/100 μl) into the right back flank of each 7-week-old mouse. Three-minute laser Doppler flowmetry (LDF) signals were measured in 60 nude mice. The data sequences were obtained at 1, 2, and 3 weeks after injecting CT26 cells. Mouse tissue samples were cut into sections and examined microscopically to determine the condition of cancer metastasis. Spectral analysis performed after 1 week revealed a significant decrease in the relative energy contribution of the endothelium-related frequency band, and significant increases in those of the myogenic and respiration-related frequency bands of the LDF signals in the metastasis group (n=12). To the best of our knowledge, this is the first study demonstrating the feasibility of evaluating metastasis in animal subjects based on changes in noninvasively measured LDF parameters. Changes in the LDF spectral indexes can be attributed to differences in the microcirculatory regulatory activities. The present measurements performed on the skin surface provide a noninvasive and real-time method for evaluating the microcirculatory responses induced by implanting CT26 tumor cells.

This paper focuses on the developments of asynchronous motor imagery (MI) based brain-computer interfaces (BCIs) applications, signal processing and machine learning to provide some basic capabilities for consumer grade products. For the proposed MI detection technique, two channels of FC5 and FC6 according to 10–20 system over primary motor area are used to recognize 3 mental tasks of tongue, left hand and right hand movements. The amplitude features of EEG signals are extracted from power spectral analysis especially in mu rhythm (8–12 Hz) and low beta wave (12–16 Hz) bands. MI features were obtained from offline analysis, and then applied to neural network (NN) with particle swarm optimization (PSO). The classification paradigm then applied to real-time BCI for humanoid robot control applications in terms of recognized MI classes from subjects. According to the experiments of 45 trials for a healthy subject, the NN-based MI recognition accuracy with PSO is 91%.

This paper proposed a SSVEP-based brain-computer interface (BCI) for wheelchair controls. SSVEP is an evoked signal which responds to visual flickering stimuli at a specific frequency. A stimulus panel containing 12, 15, 18 and 28-Hz flickering stimuli was presented in front of users. Each flickering stimulus was used to evoke SSVEP and responded to a particular command for the wheelchair control. The power spectrum densities (PSDs) for the specific frequency bands were analyzed. A target stimuli was triggered when the PSD exceeded a defined threshold. Users were able to drive the wheelchair with forward, stop, left-turn and right-turn commands according to their intentions. Additionally, a reactive navigation scheme based on artificial potential field (APF) approach was implemented to improve the security of the proposed system. A laser scanner was outfitted for obstacle detections. The proposed wheelchair system is expected to provide a convenient, safe and comfortable mobile assistance to users suffering spinal cord injuries (SCIs).

A high efficient time-shift correlation algorithm was proposed to deal with the peak time uncertainty of P300 evoked potential for a P300-based brain-computer interface (BCI). The time-shift correlation series data were collected as the input nodes of an artificial neural network (ANN), and the classification of four LED visual stimuli was selected as the output node. Two operating modes, including fast-recognition mode (FM) and accuracy-recognition mode (AM), were realized. The proposed BCI system was implemented on an embedded system for commanding an adult-size humanoid robot to evaluate the performance from investigating the ground truth trajectories of the humanoid robot. When the humanoid robot walked in a spacious area, the FM was used to control the robot with a higher information transfer rate (ITR). When the robot walked in a crowded area, the AM was used for high accuracy of recognition to reduce the risk of collision. The experimental results showed that, in 100 trials, the accuracy rate of FM was 87.8% and the average ITR was 52.73 bits/min. In addition, the accuracy rate was improved to 92% for the AM, and the average ITR decreased to 31.27 bits/min. due to strict recognition constraints.

Bilateral arm training is a popular upper extremity exercise for patients after stroke. Conventional bilateral arm trainers such as sanding units are simply made by woods, and they cannot provide quantitative performance data for automatic assessments. Hence, continuous investigations are generally required for such reciprocal operations, and those procedures result in extra loads of caregivers. In this paper, wireless sensor network (WSN) approaches are employed to develop automatic sensor data collections and sensor data intra-communications so that rehabilitation data could be properly collected. Three WSN motes are deployed in this system. Two motes are used for a set of sanding hand blocks, and the remaining mote is used for the reciprocal exercise platform. The most important feature of our approach is that three motes can be easily attached to conventional sanding units with less wiring and setup efforts to fast realize -plus functions. In addition to the collections of kinematic performance, the accelerations, grip force, applied weight, and the angle of upper plank are also automatically collected. The collected data is further transformed as rehabilitation performance indices (RPI) to guide the users to maximize their achievements, as well as to provide rehabilitation records for diagnoses and assessments. Finally, a system prototype is produced in this project to validate our approaches.

This paper discusses the trajectory planning problem of a four-degrees-of-freedom (4-DOF) robotic manipulator with similar upper limb structures of human beings. The spatial motions of the end-effector (i.e., wrist) can be desired in terms of controlling four motors of the robotic manipulator; hence, such a configuration results in the redundancy problem. In general, Jacobian solutions perform linear approximations of inverse kinematics problems with redundancy conditions. With human beings, the same wrist position can be found from different limb postures, and these postures depend on different motion scenarios such as writing words, waving hands and shaking hands. Nevertheless, Jacobian solutions are hardly to realize specific limb motion scenarios of human beings. Therefore, this paper proposes a supervised neural network based robotic manipulator trajectory planner which constructs limb motion characteristic models according to relative joint posture features with respect to different motion scenarios. The motion features are further used to provide an auxiliary condition for eliminating the redundancy problem of the inverse kinematics as well as to meet specific motion scenarios. Finally, several trajectory planning results were evaluated in terms of the Jacobian and neural network approaches respectively by using an optical motion capture system. Experiment results demonstrated that the proposed neural network based control system performs similar motion behaviors when compared to Jacobian approaches based on the same test trajectory and motion scenario.

In this paper, a decentralized Petri-net-(PN)-based wireless sensor node architecture (PN-WSNA) is proposed to model and implement a reconfigurable cognitive sensor network. The proposed PN-WSNA is defined based on an ordinary PN. Benefits of inheriting the ordinary PN are powerful modeling capabilities of discrete event dynamic systems as well as theoretical evaluations of sensor process models. A PN-WSNA engine is implemented as a kernel program in sensor nodes so that reconfigurations of sensor process can be achieved in terms of updating tiny PN-WSNA model instead of full executable firmware codes. Therefore, this approach provides an efficient and power-saving methodology to reconfigure and update the execution scenarios in remote sensor nodes. At the same time, a PN-WSNA management server is responsible for PN-WSNA model constructions, distance sensor node administrations, and routing table managements. Each PN-WSNA sensor node is realized using a BAT mote, and a simulated distributed solar tracking system is also demonstrated to verify our approaches.

The prognosis of osteonecrosis of the femoral head is highly dependent on the grading of the lesion size. A small lesion ( 30%) is doomed to collapse if left untreated. To calculate the necrosis volume, the most accurate method is to use three-dimensional magnetic resonance imaging (MRI) segmentation method. However, in clinical practice, the commonly used methods are to multiply the area percent of involvement or to use proxy, such as the necrotic index, by multiplying the angles of necrosis on two-dimensional (2D) images. The aim of this work was to find the relationship between the angular measurement proxy and the true necrosis volume. Results from different methods were compared with those of the MRI segmentation method in 29 hips. It was found that the area percent method tended to underestimate the volume and disagreed with 48% of the hips on the grading by the MRI segmentation method. As a contrast, the agreement could be improved to 90% of the hips by an index that was deduced from the original necrotic index. This study found that to estimate the necrosis volume by 2D projections is at the expense of inaccuracy but is still satisfying for clinical use. This study also found that the angular measurement proxy could be used to extrapolate the necrosis volume, whereas the bias of the measurement and grading could be decreased.

One of the most challenging research topics in robotics is the wall climbing robot. The wall climbing robots are able to perform dangerous operation, such as cleaning the high-rise building. This paper present Trajectory Tracking of a Wheeled Wall Climbing Robot Using PID Controller. To make sure that the wheels can be always well contacted to the wall without sacrificing robot's mobility is the most important consideration for controlling the wall-climbing robot. To evaluate the performance of the robot and the proposed controller, this paper conducted experiments of several trajectory tracking. Practically, encoder sensor provides the spatial posture information for realizing PID control schemes. The sensor is connected to a field-programmable gate array (FPGA) based onboard motion controller to generate control inputs for wheel motors and suction motor according to a specific trajectory. Finally, real tests were performed with the trajectories of circle, triangle and rectangle. The results were evaluated according to the measurement of the accuracy of trajectory.

This paper aims to develop the 3D surface construction applications for the solder pastes using multi-projection images and the neural network approach. The proposed solution uses the image features of multi-projection angles as the inputs and the laser surface scanning results as the outputs of the neural network model to perform precise 3D solder paste surface construction. In this manner, the proposed methodology can measure the 3D solder paste surfaces in a precise way like the laser scanning results. The advantages of this work is to use a low cost and high speed image solution to overcome the disadvantages of high cost and slow speed laser solution while the inspection accuracy is maintained. The multi-projection images are captured from the multi-channel light source and the coaxial light source to perform precise and efficient inspections, respectively. On the other hand, the back-propagation (BP) neural network approach is used to construct the 3D solder paste surface models for various solder pad geometries. Finally, the proposed system was experimentally verified. The experimental results showed that the multi-channel light source solution with pad based learning achieves 95% volumetric accuracy in average, and the coaxial light source with sub-area based learning just achieves 80% volumetric accuracy in average when compared to the actual laser surface scanning.

The purpose of this study was to describe the surgical technique and to investigate results of a modified two-incision total hip replacement using either intraoperative fluoroscopy or imageless navigation. Twenty-nine patients (30 hips) with a minimum follow-up of one year were enrolled in this study. The patients were evaluated at 3, 6, 12 weeks, 6 months, and 1-year. The functional recovery as represented by the Harris hip score and WOMAC scale were better in the fluoroscopy group of patients at the early postoperative stage (3 wks). Thereafter, both groups showed rapid recovery with no difference in scores. Injury to the lateral femoral cutaneous nerve was the most commonly seen complication and it occurred in 6 hips (fluoroscopy 2; imageless 4). The symptoms were transient and resolved in 6 months in all 6 cases. This study demonstrated that the role of intraoperative fluoroscopy could safely be replaced by an imageless navigation system for the MIS-2 THA.

The surface mounting of electronic component is the major manufacturing technology for the electronic products in the last decade. The surface mounting technology (SMT) is an assembly process that assembles the surface mountable component (SMC) and the printed circuit board (PCB) together. The SMT mounter is an automatic assembly machine that processes the SMT assemblies in terms of the optical positioning and robotic handling. The SMT assembly consists of calibrating printed circuit board (PCB); vacuuming components form feeder stations; compensating the orientation of the vacuumed surface mountable component (SMC); and finally placing SMC chips on the PCB. In order to increase the throughput, the synchronous batch vacuuming of SMC components is designed. In addition, different types of component feeding and mixing in each batch increase the difficulties of finding the best component mounting sequence. In this paper, the optimal component placement scheduler is desired to perform higher assembly performance and to reduce the cycle time. The proposed optimal component placement scheduler is developed based on the rule based heuristic search approach. In addition, to evaluate the cycle time of each heuristic search, the route oriented Petri nets (ROPN) based SMT assembly models are constructed. The optimal component placement scheduler can be further determined in terms of evaluating the ROPN SMT assembly models. Finally, the practical test PCB board data is discussed in this paper.

Manufacturing systems are hardly modelled and analysed in detail due to the complex and interactive behaviours of the production, movement, maintenance and dispatch on the shopfloor. In this paper, an agent-based modelling methodology is proposed to model the manufacturing systems using the separation model design approach. The agent models are constructed using the distributed agent-oriented Petri net (DAOPN). The DAOPN is a high-level Petri net (PN) and is designed based upon the coloured time Petri net (CTPN). The new designed DAOPN is especially desired to model the manufacturing systems in the separation and decomposition manners to reduce the modelling efforts and increase the modelling extensibility. The proposed DAOPN components include the immediate, pitch-type, catch-type, status-source and status-duplication places; immediate, timed, decision and database-accessing transitions; and directed, inhibitor and interrupt arcs. In addition to the separation characteristics, the DAOPN can also model ma...

The semiconductor manufacturing system has become one of the most important manufacturing systems in recent years. Intrabay automation for wafer transport is in high demand in a 300 mm foundry fab. The control of the transport system plays an important roles in manufacturing efficiency and the satisfaction of production strategy. In general, efficiency is the most important issue that has appeared in most research of automated transport systems. However, how to dynamically adjust the transport policy to meet the production strategy and to increase the transport efficiency as well seems to be more crucial to modern semiconductor manufacturing systems. In this paper, a fuzzy-logic-based multimission-oriented overhead vehicle dispatcher is developed. The vehicle dispatching rule is assigned in real-time according to the statistics of the manufacturing performance. In this manner, the dispatching rules can be adjusted according to possible high-risk lots so that most of the production strategies can be satisfied. If all of the lots meet the prescribed production strategies, then the nearest-job-first rule can be used to offer higher transport efficiency. In addition, the proposed vehicle dispatcher is also capable of deadlock-free operation, collision avoidance, and blockage prevention. Finally, this paper uses AutoMod simulation software to construct and evaluate the manufacturing models. By evaluating the simulation results, the proposed intelligent multimission-oriented vehicle dispatcher performs better performance than the others, and all of the production strategies are satisfied .

This paper presents the development of surgical navigation robot, which is designed based on the image servo tracking technique. The surgical navigation robot plays an important role to the computer aided surgery (CAS), since it provides the patient's space coordinate during surgical navigation stage in real-time. Especially, the proposed active image servo tracking based surgical navigation robot can track the surgical marker that is mounted on the patient's hard tissue of the surgical position, so that the navigation space can be automatically extended. The proposed surgical navigation robot system consists of the in-lab designed dual-axis eye-in-hand robot (EIHR), digital signal processor (DSP) based EIHR motion controller, image servo tracking and positioning software. The EIHR robot is composed of the dual-axis robot mechanics and two CCD cameras, which acts as the stereoscopic image capture platform. The DSP based EIHR motion controller is designed to control the EIHR robot in a desired velocity, so that the surgical marker can be dynamically tracked. The image servo tracking and positioning software is the kernel of this work, and it is composed of image capture and recognition module, fuzzy logic based surgical marker tracking module and surgical marker positioning module. The image capture and recognition module is developed to abstract the image features of the surgical marker. The intelligent fuzzy logic based surgical marker tracking module is capable of generating robot's control command so that the surgical marker can be tracked within the desired target window. In addition, the surgical marker positioning module is used to calculate the surgical marker's space coordinates in terms of the features of stereoscopic images and the robot's posture. Finally, the prototype had been finished, and the experiment results showed that proposed EIHR achieved 1.7 mm position error within 500 mm operation range.